[chrony-users] measuring accuracy of time synchronization among group of servers

[ Thread Index | Date Index | More chrony.tuxfamily.org/chrony-users Archives ]


I have a cluster of servers KLCEPH01-05 in a lab, that I must maintain synchronized clocks on to maintain cluster consistency.clock being accurately synced to real time is always a plus, but not a strict requirement in this case.
I've set up Chrony on the servers, and configured all servers with the same external upstream source, (currently dk..pool.ntp org, but experimenting to find the best source). Furthermore, I've set up all clustermembers to use each others as peers. My challenge now is to determine the accuracy to which these servers are synchronized relative to each other.
Output from chronyc sources -v from KLCEPH02 produce the following result:
root@KLCEPH02:~# chronyc sources -v
210 Number of sources = 8

  .-- Source mode  '^' = server, '=' = peer, '#' = local clock.
 / .- Source state '*' = current synced, '+' = combined , '-' = not combined,
| /   '?' = unreachable, 'x' = time may be in error, '~' = time too variable.
||                                                 .- xxxx [ yyyy ] +/- zzzz
||      Reachability register (octal) -.           |  xxxx = adjusted offset,
||      Log2(Polling interval) --.      |          |  yyyy = measured offset,
||                                \     |          |  zzzz = estimated error.
||                                 |    |           \
MS Name/IP address         Stratum Poll Reach LastRx Last sample              
===============================================================================
^+ time.cloudflare.com           3  10   377   489  -1763us[-1763us] +/-   12ms
^* 5.103.128.88.static.fibi>     1  10   377   510  -1913us[-1891us] +/- 7726us
^- matrix.rxtx.dk                2  10   377    45  -2797us[-2797us] +/-   26ms
^+ sweetums.eng.tdc.net          2  10   377   273  -2036us[-2036us] +/-   29ms
=+ klceph01.kepp.tech            2   6   377    21   +459us[ +459us] +/- 8107us
=- KLCEPH03.kepp.tech            4   8   275  478m   +138us[ -647us] +/- 9145us
=- klceph04.kepp.tech            3   6   377    68   -353us[ -353us] +/- 8980us
=+ klceph05.kepp.tech            3   8   373   221   -212us[ -212us] +/- 7752us


my impression is, that taking abs(xxxx) + abs(zzzz), would be a good meassure for the upper bound of how well, the servers are actually in sync ( about 8-10 ms in the example above). Is this interpretation correct, or is there a better way of determining a bound of their  current internal clock accuracy?

Best Regards
Simon Kepp
Kepp Technologies


Mail converted by MHonArc 2.6.19+ http://listengine.tuxfamily.org/